© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 9664
    Prev
    Next
    INDEX
    Explanations

    references to musical elements and compositions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ابتد
    -0.14
    fork
    -0.14
    δÏģα
    -0.14
    ffa
    -0.13
    cripts
    -0.13
    第ä¸Ģ次
    -0.13
    ogle
    -0.13
    caster
    -0.13
    FIRST
    -0.13
    opens
    -0.13
    POSITIVE LOGITS
     final
    0.73
    final
    0.59
     Final
    0.56
     finale
    0.55
    -final
    0.54
     FINAL
    0.53
    Final
    0.50
    æľĢåIJİ
    0.48
    _final
    0.48
    (final
    0.48
    Activations Density 0.513%

    No Known Activations